8 papers
SQuad: Sub-Quadratic Attention Distillation for Efficient Video Generation
Animesh Karnewar, Denis Korzhenkov, Amirhossein Habibian +1
Video Diffusion Transformers (DiTs) spend most of their compute inside the Self-Attention operation, whose cost grows quadratically, , with the number of latent t…
MobileWan: Closing the Quality Gap for Mobile Video Diffusion
Mohsen Ghafoorian, Denis Korzhenkov, Adil Karjauv +9
Recent advances in video diffusion have been driven by scaling transformer-based architectures to billions of parameters, substantially improving visual fidelity and motion coheren…
HLA: Hadamard Linear Attention
Hanno Ackermann, Hong Cai, Mohsen Ghafoorian +1
The attention mechanism is an important reason for the success of transformers. It relies on computing pairwise relations between tokens. To reduce the high computational cost of s…
PyramidalWan: On Making Pretrained Video Model Pyramidal for Efficient Inference
Denis Korzhenkov, Adil Karjauv, Animesh Karnewar +2
Recently proposed pyramidal models decompose the conventional forward and backward diffusion processes into multiple stages operating at varying resolutions. These models handle in…
ReHyAt: Recurrent Hybrid Attention for Video Diffusion Transformers
Mohsen Ghafoorian, Amirhossein Habibian
Recent advances in video diffusion models have shifted towards transformer-based architectures, achieving state-of-the-art video generation but at the cost of quadratic attention c…
Neodragon: Mobile Video Generation using Diffusion Transformer
Animesh Karnewar, Denis Korzhenkov, Ioannis Lelekas +10
We introduce Neodragon, a text-to-video system capable of generating 2s (49 frames @24 fps) videos at the 640x1024 resolution directly on a Qualcomm Hexagon NPU in a record 6.7s (7…